Abstract
Background: We developed multifactorial models for predicting incident dementia and brain pathology in the oldest old using the Vantaa 85+ cohort. Methods: We included participants without dementia at baseline and at least 2 years of follow-up (N = 245) for dementia prediction or with autopsy data (N = 163) for pathology. A supervised machine learning method was used for model development, considering sociodemographic, cognitive, clinical, vascular, and lifestyle factors, as well as APOE genotype. Neuropathological assessments included β-amyloid, neurofibrillary tangles and neuritic plaques, cerebral amyloid angiopathy (CAA), macro- and microscopic infarcts, α-synuclein pathology, hippocampal sclerosis, and TDP-43. Results: Prediction model performance was evaluated using AUC for 10 × 10-fold cross-validation. Overall AUCs were 0.73 for dementia, 0.64-0.68 for Alzheimer's disease (AD)- or amyloid-related pathologies, 0.72 for macroinfarcts, and 0.61 for microinfarcts. Predictors for dementia were different from those in previous reports of younger populations; for example, age, sex, and vascular and lifestyle factors were not predictive. Predictors for dementia versus pathology were also different, because cognition and education predicted dementia but not AD- or amyloid-related pathologies. APOE genotype was most consistently present across all models. APOE alleles had a different impact: ϵ4 did not predict dementia, but it did predict all AD- or amyloid-related pathologies; ϵ2 predicted dementia, but it was protective against amyloid and neuropathological AD; and ϵ3ϵ3 was protective against dementia, neurofibrillary tangles, and CAA. Very few other factors were predictive of pathology. Conclusions: Differences between predictors for dementia in younger old versus oldest old populations, as well as for dementia versus pathology, should be considered more carefully in future studies.
| Original language | English |
|---|---|
| Article number | 11 |
| Pages (from-to) | 11 |
| Journal | Alzheimer's Research and Therapy |
| Volume | 11 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - 22 Jan 2019 |
| MoE publication type | A1 Journal article-refereed |
Fingerprint
Keywords
- Dementia
- Neuropathology
- Oldest old
- Prediction
- Supervised machine learning
Cite this
}
Prediction models for dementia and neuropathology in the oldest old : The Vantaa 85+ cohort study 11 Medical and Health Sciences 1109 Neurosciences. / Hall, Anette; Pekkala, Timo; Polvikoski, Tuomo; van Gils, Mark; Kivipelto, Miia; Lötjönen, Jyrki; Mattila, Jussi; Kero, Mia; Myllykangas, Liisa; Mäkelä, Mira; Oinas, Minna; Paetau, Anders; Soininen, Hilkka; Tanskanen, Maarit; Solomon, Alina (Corresponding Author).
In: Alzheimer's Research and Therapy, Vol. 11, No. 1, 11, 22.01.2019, p. 11.Research output: Contribution to journal › Article › Scientific › peer-review
TY - JOUR
T1 - Prediction models for dementia and neuropathology in the oldest old
T2 - The Vantaa 85+ cohort study 11 Medical and Health Sciences 1109 Neurosciences
AU - Hall, Anette
AU - Pekkala, Timo
AU - Polvikoski, Tuomo
AU - van Gils, Mark
AU - Kivipelto, Miia
AU - Lötjönen, Jyrki
AU - Mattila, Jussi
AU - Kero, Mia
AU - Myllykangas, Liisa
AU - Mäkelä, Mira
AU - Oinas, Minna
AU - Paetau, Anders
AU - Soininen, Hilkka
AU - Tanskanen, Maarit
AU - Solomon, Alina
PY - 2019/1/22
Y1 - 2019/1/22
N2 - Background: We developed multifactorial models for predicting incident dementia and brain pathology in the oldest old using the Vantaa 85+ cohort. Methods: We included participants without dementia at baseline and at least 2 years of follow-up (N = 245) for dementia prediction or with autopsy data (N = 163) for pathology. A supervised machine learning method was used for model development, considering sociodemographic, cognitive, clinical, vascular, and lifestyle factors, as well as APOE genotype. Neuropathological assessments included β-amyloid, neurofibrillary tangles and neuritic plaques, cerebral amyloid angiopathy (CAA), macro- and microscopic infarcts, α-synuclein pathology, hippocampal sclerosis, and TDP-43. Results: Prediction model performance was evaluated using AUC for 10 × 10-fold cross-validation. Overall AUCs were 0.73 for dementia, 0.64-0.68 for Alzheimer's disease (AD)- or amyloid-related pathologies, 0.72 for macroinfarcts, and 0.61 for microinfarcts. Predictors for dementia were different from those in previous reports of younger populations; for example, age, sex, and vascular and lifestyle factors were not predictive. Predictors for dementia versus pathology were also different, because cognition and education predicted dementia but not AD- or amyloid-related pathologies. APOE genotype was most consistently present across all models. APOE alleles had a different impact: ϵ4 did not predict dementia, but it did predict all AD- or amyloid-related pathologies; ϵ2 predicted dementia, but it was protective against amyloid and neuropathological AD; and ϵ3ϵ3 was protective against dementia, neurofibrillary tangles, and CAA. Very few other factors were predictive of pathology. Conclusions: Differences between predictors for dementia in younger old versus oldest old populations, as well as for dementia versus pathology, should be considered more carefully in future studies.
AB - Background: We developed multifactorial models for predicting incident dementia and brain pathology in the oldest old using the Vantaa 85+ cohort. Methods: We included participants without dementia at baseline and at least 2 years of follow-up (N = 245) for dementia prediction or with autopsy data (N = 163) for pathology. A supervised machine learning method was used for model development, considering sociodemographic, cognitive, clinical, vascular, and lifestyle factors, as well as APOE genotype. Neuropathological assessments included β-amyloid, neurofibrillary tangles and neuritic plaques, cerebral amyloid angiopathy (CAA), macro- and microscopic infarcts, α-synuclein pathology, hippocampal sclerosis, and TDP-43. Results: Prediction model performance was evaluated using AUC for 10 × 10-fold cross-validation. Overall AUCs were 0.73 for dementia, 0.64-0.68 for Alzheimer's disease (AD)- or amyloid-related pathologies, 0.72 for macroinfarcts, and 0.61 for microinfarcts. Predictors for dementia were different from those in previous reports of younger populations; for example, age, sex, and vascular and lifestyle factors were not predictive. Predictors for dementia versus pathology were also different, because cognition and education predicted dementia but not AD- or amyloid-related pathologies. APOE genotype was most consistently present across all models. APOE alleles had a different impact: ϵ4 did not predict dementia, but it did predict all AD- or amyloid-related pathologies; ϵ2 predicted dementia, but it was protective against amyloid and neuropathological AD; and ϵ3ϵ3 was protective against dementia, neurofibrillary tangles, and CAA. Very few other factors were predictive of pathology. Conclusions: Differences between predictors for dementia in younger old versus oldest old populations, as well as for dementia versus pathology, should be considered more carefully in future studies.
KW - Dementia
KW - Neuropathology
KW - Oldest old
KW - Prediction
KW - Supervised machine learning
UR - http://www.scopus.com/inward/record.url?scp=85060370934&partnerID=8YFLogxK
U2 - 10.1186/s13195-018-0450-3
DO - 10.1186/s13195-018-0450-3
M3 - Article
C2 - 30670070
AN - SCOPUS:85060370934
VL - 11
SP - 11
JO - Alzheimer's Research and Therapy
JF - Alzheimer's Research and Therapy
SN - 1758-9193
IS - 1
M1 - 11
ER -